SOTAVerified

Instruction Following

Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 1135 papers

TitleStatusHype
Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models—0
From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data—0
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study—0
StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation—0
RECAST: Strengthening LLMs' Complex Instruction Following with Constraint-Verifiable Data—0
STRICT: Stress Test of Rendering Images Containing TextCode1
Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language ModelsCode1
Optimal Transport-Based Token Weighting scheme for Enhanced Preference OptimizationCode0
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ TasksCode1
MIDB: Multilingual Instruction Data Booster for Enhancing Multilingual Instruction Synthesis—0
Show:102550
← PrevPage 7 of 114Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AutoIF (Llama3 70B)Inst-level loose-accuracy90.4—Unverified
2AutoIF (Qwen2 72B)Inst-level loose-accuracy88—Unverified
3GPT-4Inst-level loose-accuracy85.37—Unverified
4PaLM 2 SInst-level loose-accuracy59.11—Unverified